Anthropic shares official prompt to stop Claude from sounding like Claude
alex_verem · x · 2026-09-09
Anthropic shared an official prompt that suppresses Claude's signature "mannered prose." The author reports it improves writing across Claude Fable 5.1, GPT-5.6 Sol, and GPT-6 Astra — paste it into custom instructions.
The core diagnosis: mannered prose substitutes metaphor and flourish for direct statement ("a dial worth turning" instead of "a parameter worth varying"), performing the writer rather than conveying the idea, and dragging in unchosen connotations. The fix: when a literal phrase is available, use it.
Related event: Anthropic's Writing Prompt Goes Viral, Fixing 'Claude Voice' and Beyond(3 posts)→
More from Models
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27